{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AS377QK5MIYB5JSINU3WOWXXTT","short_pith_number":"pith:AS377QK5","schema_version":"1.0","canonical_sha256":"04b7ffc15d62301ea6486d37675af79ced9ee083889067b948b07271d2d34489","source":{"kind":"arxiv","id":"2402.01722","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eden Chung, Fatima Javid, Katherine Jijo, Liang Zhang, Natan Vidra, Spurthi Setty, Tommy Clifford","submitted_at":"2024-01-27T00:18:07Z","abstract_excerpt":"Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models. The objective is to enhance AI models through continuous feedback loops, utilizing metrics such as cosine similarity, LLM evaluation and Rouge-L scores to evaluate the models. Leveraging LLMs like GPT-3.5, GPT4ALL, and LLaMA2, and Claude, this approach is benchmarked on fina"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2402.01722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-27T00:18:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fdef184ee91a52be111bc46a676cfdaa22d240c7f4b6f07b97a98d73ce5d2b58","abstract_canon_sha256":"802ad3b1ed25ab118b219c6cb9076279b04839cfc1726f4b49a934ffc0386a20"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:05.641575Z","signature_b64":"kPlluUcFtux3bedS/XW1K7fbqO4oxIw5dgwKL9BYx6LQ5VCYsfhGqi5zDKEkEB2ZDx2MNrT/vllXdkKfkDIyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"04b7ffc15d62301ea6486d37675af79ced9ee083889067b948b07271d2d34489","last_reissued_at":"2026-07-05T07:41:05.641134Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:05.641134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Large Language Model Performance To Answer Questions and Extract Information More Accurately","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eden Chung, Fatima Javid, Katherine Jijo, Liang Zhang, Natan Vidra, Spurthi Setty, Tommy Clifford","submitted_at":"2024-01-27T00:18:07Z","abstract_excerpt":"Large Language Models (LLMs) generate responses to questions; however, their effectiveness is often hindered by sub-optimal quality of answers and occasional failures to provide accurate responses to questions. To address these challenges, a fine-tuning process is employed, involving feedback and examples to refine models. The objective is to enhance AI models through continuous feedback loops, utilizing metrics such as cosine similarity, LLM evaluation and Rouge-L scores to evaluate the models. Leveraging LLMs like GPT-3.5, GPT4ALL, and LLaMA2, and Claude, this approach is benchmarked on fina"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01722","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.01722/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2402.01722","created_at":"2026-07-05T07:41:05.641198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.01722v1","created_at":"2026-07-05T07:41:05.641198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01722","created_at":"2026-07-05T07:41:05.641198+00:00"},{"alias_kind":"pith_short_12","alias_value":"AS377QK5MIYB","created_at":"2026-07-05T07:41:05.641198+00:00"},{"alias_kind":"pith_short_16","alias_value":"AS377QK5MIYB5JSI","created_at":"2026-07-05T07:41:05.641198+00:00"},{"alias_kind":"pith_short_8","alias_value":"AS377QK5","created_at":"2026-07-05T07:41:05.641198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19396","citing_title":"BioHarness: Substrate-Aware Evidence Assembly for Biomedical Question Answering across Literature, Knowledge Bases, and Biological Atlases","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20571","citing_title":"Less is More: Lightweight Prompt Compression for Question Answering Applications on Edge Devices","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT","json":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT.json","graph_json":"https://pith.science/api/pith-number/AS377QK5MIYB5JSINU3WOWXXTT/graph.json","events_json":"https://pith.science/api/pith-number/AS377QK5MIYB5JSINU3WOWXXTT/events.json","paper":"https://pith.science/paper/AS377QK5"},"agent_actions":{"view_html":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT","download_json":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT.json","view_paper":"https://pith.science/paper/AS377QK5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.01722&json=true","fetch_graph":"https://pith.science/api/pith-number/AS377QK5MIYB5JSINU3WOWXXTT/graph.json","fetch_events":"https://pith.science/api/pith-number/AS377QK5MIYB5JSINU3WOWXXTT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT/action/storage_attestation","attest_author":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT/action/author_attestation","sign_citation":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT/action/citation_signature","submit_replication":"https://pith.science/pith/AS377QK5MIYB5JSINU3WOWXXTT/action/replication_record"}},"created_at":"2026-07-05T07:41:05.641198+00:00","updated_at":"2026-07-05T07:41:05.641198+00:00"}